Precision Least Squares: Estimation and Inference in High-Dimensions
(2025) In Journal of Business & Economic Statistics- Abstract
- The least squares estimator can be cast as depending only on the precision matrix of the data, similar to the weights of a global minimum variance portfolio. We give conditions under which any plug-in precision matrix estimator produces an unbiased and consistent least squares estimator for stationary time series regressions, in both low- and high-dimensional settings. Such conditions define a class of “Precision Least Squares” (PrLS) estimators, which are shown to be approximately Gaussian, efficient, and to provide automatic family-wise error control in large samples. For estimating high-dimensional sparse regression models, we propose a LASSO Cholesky estimator of the plug-in precision matrix. We show its consistency and how to properly... (More)
- The least squares estimator can be cast as depending only on the precision matrix of the data, similar to the weights of a global minimum variance portfolio. We give conditions under which any plug-in precision matrix estimator produces an unbiased and consistent least squares estimator for stationary time series regressions, in both low- and high-dimensional settings. Such conditions define a class of “Precision Least Squares” (PrLS) estimators, which are shown to be approximately Gaussian, efficient, and to provide automatic family-wise error control in large samples. For estimating high-dimensional sparse regression models, we propose a LASSO Cholesky estimator of the plug-in precision matrix. We show its consistency and how to properly bias correct it, thereby obtaining a LASSO Cholesky-based PrLS (LC-PrLS) estimator. LC-PrLS performs well in finite samples and better than state-of-the-art high-dimensional estimators. We employ LC-PrLS to investigate the dynamic network of predictive connections among a large set of global bank stock returns. We find that crisis years correspond to a collapse of predictive linkages. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3e85f58a-ccb6-44ed-b39d-1c53e70661ed
- author
- Margaritella, Luca LU and Sessinou, Rosnel
- organization
- publishing date
- 2025-02
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Precision Least Squares, High-Dimensional Inference, Predictive Networks, C32, C55, C12, G19
- in
- Journal of Business & Economic Statistics
- publisher
- Taylor & Francis
- external identifiers
-
- scopus:85217036888
- ISSN
- 1537-2707
- DOI
- 10.1080/07350015.2024.2440573
- language
- English
- LU publication?
- yes
- id
- 3e85f58a-ccb6-44ed-b39d-1c53e70661ed
- date added to LUP
- 2024-12-17 16:10:48
- date last changed
- 2025-04-09 09:49:56
@article{3e85f58a-ccb6-44ed-b39d-1c53e70661ed, abstract = {{The least squares estimator can be cast as depending only on the precision matrix of the data, similar to the weights of a global minimum variance portfolio. We give conditions under which any plug-in precision matrix estimator produces an unbiased and consistent least squares estimator for stationary time series regressions, in both low- and high-dimensional settings. Such conditions define a class of “Precision Least Squares” (PrLS) estimators, which are shown to be approximately Gaussian, efficient, and to provide automatic family-wise error control in large samples. For estimating high-dimensional sparse regression models, we propose a LASSO Cholesky estimator of the plug-in precision matrix. We show its consistency and how to properly bias correct it, thereby obtaining a LASSO Cholesky-based PrLS (LC-PrLS) estimator. LC-PrLS performs well in finite samples and better than state-of-the-art high-dimensional estimators. We employ LC-PrLS to investigate the dynamic network of predictive connections among a large set of global bank stock returns. We find that crisis years correspond to a collapse of predictive linkages.}}, author = {{Margaritella, Luca and Sessinou, Rosnel}}, issn = {{1537-2707}}, keywords = {{Precision Least Squares; High-Dimensional Inference; Predictive Networks; C32; C55; C12; G19}}, language = {{eng}}, publisher = {{Taylor & Francis}}, series = {{Journal of Business & Economic Statistics}}, title = {{Precision Least Squares: Estimation and Inference in High-Dimensions}}, url = {{http://dx.doi.org/10.1080/07350015.2024.2440573}}, doi = {{10.1080/07350015.2024.2440573}}, year = {{2025}}, }